|
|
Advanced methods for sleep quality assessment
Doležalová, Anna ; Králík, Martin (referee) ; Ronzhina, Marina (advisor)
This diploma thesis is focused on advanced sleep assessment using deep learning. Metrics for sleep assessment and their use are described here. There are hearth rate and accelerometer data from Apple Watch used for classification. The basis for the classification was a model composed of 1D convolution networks in combination with recurrent neural network. LSTM and GRU were used as recurrent networks. Models were taught to classify into two, three and five phases. At last the resulting methods are compared.
|
|
|
Ppg Signal Quality Assessment And Heart Rate Estimation
Vargová, Enikö
The presented paper describes an algorithm for signal quality assessment based on clusteranalysis and also an algorithm for heart rate estimation from PPG signals. This work includesa database which comprises 48 PPG signals collected by a smartphone and 48 ECG signals recordedby an ECG recorder. The accuracy of the quality assessment is 97,5 % on the training set and87,5 % on the test set. The average deviation of the estimated heart rate is 1,39889 bpm.
|
|
|
PPG signal quality assessment and heart rate estimation
Vargová, Enikö ; Vítek, Martin (referee) ; Němcová, Andrea (advisor)
This work deals with photoplethysmographic (PPG) signals, their processing, quality assessment, estimation of heart rate from PPG signals and the ability to record biological signals with smartphones. The aim of this work is to record PPG signals using a smartphone and reference ECG signals using an ECG recorder. The work also includes the design of two algorithms, one for signal quality assessment and the other for heart rate estimation from PPG signals.
|
|
| |
|
| |
|
|
Analysis of pulse wave propagation in aorta
Tichoň, Dušan ; Klas, Roman (referee) ; Burša, Jiří (advisor)
The aim of this diploma thesis is to assess the applicability of pulse wave propagation monitoring in the cardiovascular system in the field of prediction and early diagnosis of abdominal aortic aneurysm (AAA). The very first part is focused on description of heart and blood vessels with its pathological changes in presence of aneurysm. For this reason, current methods of monitoring and surgical treating of AAA were mentioned. Due to their difficult clinical use widely in the population, new methods based on pulse wave monitoring were presented. Using an analytical approach we estimated the difference in the arrival of the pulse wave at measurable locations between healthy and pathological aorta in the order of miliseconds. By experimental monitoring using photoplethysmographic sensors, we observed significant changes of pulse wave velocity with respect to the mechanical properties of the artery wall (mainly associated with age), which we tried to implement by hyperelastic material models used in computational simulations of pulse wave proagation on simplified geometries by fluid structure interaction method. These analyzes should verify applicability of FSI simulations in further development of diagnostic methods of AAA.
|
|
|
Blood pressure estimation using smartphone
Vařečka, Martin ; Vítek, Martin (referee) ; Němcová, Andrea (advisor)
Blood pressure is one of the basic indicators of the health state of the cardiovascular system. High blood pressure is the main risk factor of ischemic heart disease, atherosclerosis and stroke. Therefore, it is important to monitor long-term changes in blood pressure and respond in time to these changes. Blood pressure meters are not standard household equipment, while a well-equipped smartphone is. Smartphones contain a large number of sensors capable of measuring biomedical signals. This thesis focuses on creating an application capable of determining blood pressure using data obtained from these sensors.
|
|
|
Analyzer of cardiac waveform
Zmeškal, Ladislav ; Říha, Kamil (referee) ; Číž, Radim (advisor)
The thesis describes design, algorithmization and realization of graphical application for recording EKG and PPG signal using LabJack UE9 tool in Matlab program, it also describes subsequent deposition of recorded signals and their processing, such as optional selection, cropping and filtering. Furthermore there are described types of filters, methods for detecting basic parameters of EKG and PPG signals and methods for detecting R waves and Systolic peaks. Based on detection of those parameters, algorithms for computing average heart rate and finding arrhythmias were designed and tested. Last part of the thesis includes an evaulation which compares values detected by designed algorithms with values from public database which includes reference annotation.
|
guest ::
